Plugins

API regression and acceptance workbench: snapshot the responses of the endpoints you register before the agent edits the backend, rerun them all after the edit, and review a structured field-level diff (status codes, added and removed fields, numeric old → new values with the delta) beside the captured source diff, accepting each endpoint one by one before exporting a Markdown or single-file HTML report.

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

The Space Lens workbench as a DeepSeek Harness panel: the directory the current session is working in, scanned and explored by Space Lens itself.

Generate and edit images, generate video, and cut video locally through a GenBox server, with a zero-key test bench.

Retrospective agent-session evaluation — grades the sessions that already happened: deterministic grade cards, regression diffs, /eval-history trends, and /eval --report straight from exported artifacts; no benchmark runs, no LLM judges.

中瑞世联工作台 / CRWU audit workbench for DeepSeek Harness: pick a pending audit report, dispatch one AI audit subagent, watch and stop/restart it, auto-upload deliverables to Aliyun OSS.

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

Run the same prompt through every model you have, and see the difference without squinting.

Version-control workbench for the DSH Web sidebar: local changes grouped by type, per-file and multi-file staging, preview-confirmed commit / update / push, and a failure dialog that shows the raw Git output instead of a four-second toast.

Local relationship-memory workbench with a confirmation gate: every AI write — extracted memories and newly created contacts alike — lands in a pending queue until the user confirms it in the GUI; materials are archived verbatim with quote-level provenance checks on AI extraction, and confirmed memories aggregate into per-contact timelines, gift occasions and reciprocity views. Ships a native relationship agent preset for conversation capture; JSON storage by default with an optional SQLite backend, zero production dependencies.

The dock-base Workbench adapter for the DSH Quick Control panel. The panel core ships separately as `dsh-flash`; this package is what mounts it into dock-base — sidebar/floating panel, activity-bar ⚡, editor view and the dock-flash:openQuickControl command. Requires dock-base; a broken install fails loudly instead of silently doing nothing.

Personal workbench panel with an overview dashboard, custom kanban boards, a note pad and a file library, persisted to local JSON by the host.

OpenReelbench, the open video creative bench for DeepSeek Harness: a gated four-stage pipeline (brief -> script -> assets -> compose) that turns one sentence into a narrated explainer video; generation via ComfyUI workflows, assembly with FFmpeg. / DSH 开源

Post-punk zine-collage visual skin for the DSH Web workbench.

Extensible DSH Web workbench host with durable instances, templates, and page, panel, and capsule presentations

A persistent DevRel workbench for official DeepSeek Harness Discussions: triage, topics and evidence-first reporting.

LiveBench leaderboard for DSH — discovers the release the official site currently publishes, then reads its CSV and category JSON, and renders model rankings in an isolated same-origin iframe opened from a button beside the composer. Search, organization / open-weight / reasoning filters, per-category sorting, task-level detail, up to four models side by side, CSV export; refreshes every 60 s by default (configurable 30–3600) and caches only to the plugin's own .cache/rankings.json.

Self-media workbench plugin: 8-tab dashboard (daily brief, narrative lines, topics, drafts, knowledge-card distill review, sources, publish, advice) with hard guards (48h window, event dedup, card/line existence, read-only advice) and a read-only intel module following the four red lines.

EN: Windows-only HarmonyOS workbench with 41 dcli tools and native agent presets for DeepSeek Harness. ZH: 面向 DeepSeek Harness 的 Windows 原生鸿蒙开发工作台，包含 41 个 dcli 工具与原生鸿蒙预设。

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and

Multi-bot workbench for DeepSeek Harness: bridges the sdk-bots orchestration gateway (group chats, single bots) into the dsh web shell with official-styled UI.

Alibaba Cloud Workbench CLI plugin — lets DeepSeek Harness's Agent directly control remote ECS instances.

Local Qimen business-timing workbench for DeepSeek Harness, with nine palaces, deterministic scoring, future-window ranking, and direction advice.